From a18a8292e2b4fcd9d10f4a23ed208fb47dcdea5b Mon Sep 17 00:00:00 2001
From: Yineng Zhang <me@zhyncs.com>
Date: Mon, 26 Aug 2024 16:51:15 +1000
Subject: [PATCH] docs: update README (#877)

SGLang support Qwen2 MOE ref https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/models/qwen2_moe.py
---
 README.md | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/README.md b/README.md
index 5edba56f..10e729d3 100644
--- a/README.md
+++ b/README.md
@@ -236,11 +236,6 @@ print("Chat response:", chat_response)
 
 ### SGLang
 
-> [!NOTE]
-> <div align="center">
-> SGLang now does NOT support the <b>Qwen2MoeForCausalLM</b> architecture, thus making <b>Qwen2-57B-A14B</b> incompatible.
-> </div>
-
 Please install `SGLang` from source. Similar to `vLLM`, you need to launch a server and use OpenAI-compatible API service. Start the server first:
 ```shell
 python -m sglang.launch_server --model-path Qwen/Qwen2-7B-Instruct --port 30000